{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:I5BPQUBY2QQLXTKFUC5NINO7NF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0eb366af7fcba7058c66cf37768778af2d324569d7b80addae1b1d3294a299ba","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-01-05T15:07:10Z","title_canon_sha256":"d27c49b6618548186743871a8875e7e42525ff95a6463bd3240797a1fb137960"},"schema_version":"1.0","source":{"id":"2301.02099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02099","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02099v1","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02099","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_12","alias_value":"I5BPQUBY2QQL","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_16","alias_value":"I5BPQUBY2QQLXTKF","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_8","alias_value":"I5BPQUBY","created_at":"2026-07-05T05:30:56Z"}],"graph_snapshots":[{"event_id":"sha256:05e44a6dd1e487f0e310fd2fe72d357c1c1f00c7f877d7df1d6faf23a8d40473","target":"graph","created_at":"2026-07-05T05:30:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.02099/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing agents that can execute multiple skills by learning from pre-collected datasets is an important problem in robotics, where online interaction with the environment is extremely time-consuming. Moreover, manually designing reward functions for every single desired skill is prohibitive. Prior works targeted these challenges by learning goal-conditioned policies from offline datasets without manually specified rewards, through hindsight relabelling. These methods suffer from the issue of sparsity of rewards, and fail at long-horizon tasks. In this work, we propose a novel self-supervise","authors_text":"Alessandro Lazaric, Karteek Alahari, Lina Mezghani, Piotr Bojanowski, Sainbayar Sukhbaatar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-01-05T15:07:10Z","title":"Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02099","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9497546bc0c2edd5d24f7549a2b996e5c06ffa77c0e285fa20b2b58afa5233e0","target":"record","created_at":"2026-07-05T05:30:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0eb366af7fcba7058c66cf37768778af2d324569d7b80addae1b1d3294a299ba","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-01-05T15:07:10Z","title_canon_sha256":"d27c49b6618548186743871a8875e7e42525ff95a6463bd3240797a1fb137960"},"schema_version":"1.0","source":{"id":"2301.02099","kind":"arxiv","version":1}},"canonical_sha256":"4742f85038d420bbcd45a0bad435df694ac4bca6760cb499564e1cab0ef0fbe3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4742f85038d420bbcd45a0bad435df694ac4bca6760cb499564e1cab0ef0fbe3","first_computed_at":"2026-07-05T05:30:56.864563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:56.864563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8vQ2sx23jsp6lWGrJbXzSOUN++IClvr0hFM0rE13O3UakhgGp/fM91zMtl1qpzzdIofpA6fhzTNzeVEJy97ODA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:56.865017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.02099","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9497546bc0c2edd5d24f7549a2b996e5c06ffa77c0e285fa20b2b58afa5233e0","sha256:05e44a6dd1e487f0e310fd2fe72d357c1c1f00c7f877d7df1d6faf23a8d40473"],"state_sha256":"3146fce83758e964f9e2eaa1d5f036a5dac0ced1a474f6ffaff443efe3f9299a"}